11 research outputs found
ExtremeEarth meets satellite data from space
Get PDFBringing together a number of cutting-edge technologies that range from storing extremely large volumesof data all the way to developing scalable machine learning and deep learning algorithms in a distributed manner, and having them operate over the same infrastructure poses unprecedentedchallenges. One of these challenges is the integration of European Space Agency (ESA)s Thematic Exploitation Platforms (TEPs) and data information access service platforms with a data platform, namely Hopsworks, that enables scalable data processing, machine learning, and deep learning on Copernicus data, and development of very large training datasets for deep learning architectures targeting the classification of Sentinel images. In this paper, we present the software architecture of ExtremeEarth that aims at the development of scalable deep learning and geospatial analytics techniques for processing and analyzing petabytes of Copernicus data. The ExtremeEarth software infrastructure seamlessly integrates existing and novel software platforms and tools for storing, accessing, processing, analyzing, and visualizing large amounts of Copernicus data. New techniques in the areas of remote sensing and artificial intelligence with an emphasis on deep learning are developed. These techniques and corresponding software presented in thispaper are to be integrated with and used in two ESA TEPs, namely Polar and Food Security TEPs. Furthermore, we presentthe integration of Hopsworks with the Polar and Food Securityuse cases and the flow of events for the products offered through the TEPs
Glacial geomorphology and cosmogenic 10Be and 26Al exposure ages in the northern Dufek Massif, Weddell Sea embayment, Antarctica
Get PDFWe studied the glacial geomorphology and geochronology of two ice-free valleys in the Dufek
Massif (Antarctic Specially Protected Area 119) providing new constraints on past ice sheet thickness in the
Weddell Sea embayment. 10Be and 26Al cosmogenic surface exposure dating provided chronological
control. Seven glacial stages are proposed. These include an alpine glaciation, with subsequent (mid-
Miocene?) over-riding by a warm-based ice sheet. Subsequent advances are marked by a series of minor
drift deposits at 760m altitude at .1 Ma, followed by at least two later ice sheet advances that are
characterized by extensive drift sheet deposition. An advance of plateau ice field outlet glaciers from the
south postdated these drift sheets. The most recent advance involved the cold-based expansion of the ice sheet
from the north at the Last Glacial Maximum, or earlier, which deposited a series of bouldery moraines during
its retreat. This suggests at most a relatively modest expansion of the ice sheet and outlet glaciers dominated
by a lateral ice expansion of just 2–3 km and maintaining a thickness similar to that of the northern ice sheet
front. These observations are consistent with other reports of modest ice sheet thickening around the Weddell
Sea embayment during the Last Glacial Maximum
Exploring former subglacial Hodgson Lake, Antarctica Paper I: site description, geomorphology and limnology
Full text linkA polar oceans shipping information system
No full textGlobally, ships above a certain tonnage, as well as an increasing number of smaller vessels, rely on
the AIS (Automatic Identification System) to safely navigate around other vessels, which are typically
the only dynamically moving surface obstacles in most oceans. In the polar seas however, there are
additional challenges due to the dynamic nature of icebergs and sea ice. While satellite technology
has improved spatiotemporal coverage and sophistication, local observation remains invaluable for
navigating ice infested waters. An analogous system to AIS, tailored for the polar oceans, could
enhance safety by providing additional knowledge of the ice a ship is sailing through. This system
could function as a distributed communication network, which integrates data on key environmental
parameters collected from all vessels operating in polar regions which then can be used with remote
sensing products to improve situational awareness for all maritime traffic. We propose that an
international initiative to develop such a system could be pursued through a collaborative research
program utilizing national polar research vessels
Polar ice:Integrating, distributing and visualising ice information products for operators in polar waters
No full textPolar ice:Integrating, distributing and visualising ice information products for operators in polar waters
No full text
Artificial Intelligence and Big Data Technologies for Copernicus Data: The ExtremeEarth Project
No full textExtremeEarth is a three-year H2020 ICT research and innovation project which is currently in its final year. The main objective of ExtremeEarth is to develop Artificial Intelligence and Big Data techniques and technologies that scale to the large volumes of big Copernicus data, information and knowledge, and apply these technologies in two of the ESA Thematic Exploitation Platforms: Food Security and Polar. The technical contributions of the project so far include: (i) new deep learning architectures for crop type mapping in the context of the Food Security use case, (ii) new deep learning architectures for sea ice mapping in the context of the Polar use case, (iii) the development and open publication of very large datasets for training these architectures, (iv) new versions of scalable semantic technologies for managing big linked geospatial data, and (v) a new platform for bringing all the previous technologies together and applying them to the two use cases
